© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1292
    Prev
    Next
    INDEX
    Explanations

    citations of academic works, particularly in mathematics and physics, including journal names, publishers, and publication details like volume and date

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.61
     journals
    -0.58
     biographer
    -0.52
     lettera
    -0.50
     guadag
    -0.50
     журнала
    -0.50
     Вікіпе
    -0.49
     journal
    -0.48
     पत्र
    -0.47
    RetentionPolicy
    -0.47
    POSITIVE LOGITS
     ISBN
    0.76
    évaluateur
    0.70
     Италијани
    0.70
     Meksiku
    0.67
     linkovi
    0.66
    ISBN
    0.65
     lenker
    0.63
    bootstrapcdn
    0.63
    ValueStyle
    0.62
    GraphicsUnit
    0.60
    Activations Density 0.195%

    No Known Activations